Shicheng Wang, Zheng-xi Song, Hao Ding, Hao-bin Shi
In traditional reinforcement Q-Learning method, there exists two problems: difficulty of dividing the state information, complexity of extreme large dimension input. To solve these two problems, this paper proposed an improved reinforcement Q-Learning method with BP neutral network. In this method, the large Q table is replaced by a BP neural network. Continuous environmental information is the input. The Q value is the output. The Q value and weight of the network are also adjusted by the action rewards. This paper presents an algorithm for single agent's action selection. Simulation shows proposed method is more stable and applicable for the agent's strategy selection.
{"title":"An Improved Reinforcement Q-Learning Method with BP Neural Networks in Robot Soccer","authors":"Shicheng Wang, Zheng-xi Song, Hao Ding, Hao-bin Shi","doi":"10.1109/ISCID.2011.53","DOIUrl":"https://doi.org/10.1109/ISCID.2011.53","url":null,"abstract":"In traditional reinforcement Q-Learning method, there exists two problems: difficulty of dividing the state information, complexity of extreme large dimension input. To solve these two problems, this paper proposed an improved reinforcement Q-Learning method with BP neutral network. In this method, the large Q table is replaced by a BP neural network. Continuous environmental information is the input. The Q value is the output. The Q value and weight of the network are also adjusted by the action rewards. This paper presents an algorithm for single agent's action selection. Simulation shows proposed method is more stable and applicable for the agent's strategy selection.","PeriodicalId":224504,"journal":{"name":"2011 Fourth International Symposium on Computational Intelligence and Design","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123481548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Entity is an important information carrier in Web pages. Searchers often want a ranked list of relevant entities directly rather a list of documents. So the research of related entity finding (REF) is very meaningful. In this paper we investigate the most important task of REF: Entity Ranking. To address the issue of wrong entity type in entity ranking: some retrieved entities don't belong to the target entity type. We make use of category expansion to deal with the issue of wrong entity type polluting entity ranking. We use Wikipedia and Dbpedia as data sources in the experiment. We found category expansion based on original type achieves a better result in recall and precision proved by experiment.
{"title":"A Study of Category Expansion for Related Entity Finding","authors":"Junsan Zhang, Y. Qu","doi":"10.1109/ISCID.2011.55","DOIUrl":"https://doi.org/10.1109/ISCID.2011.55","url":null,"abstract":"Entity is an important information carrier in Web pages. Searchers often want a ranked list of relevant entities directly rather a list of documents. So the research of related entity finding (REF) is very meaningful. In this paper we investigate the most important task of REF: Entity Ranking. To address the issue of wrong entity type in entity ranking: some retrieved entities don't belong to the target entity type. We make use of category expansion to deal with the issue of wrong entity type polluting entity ranking. We use Wikipedia and Dbpedia as data sources in the experiment. We found category expansion based on original type achieves a better result in recall and precision proved by experiment.","PeriodicalId":224504,"journal":{"name":"2011 Fourth International Symposium on Computational Intelligence and Design","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129413723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a Peer-To-Peer (P2P) Digital Resource Management (DRM) system for video content in this paper. The encryption arithmetic of our system is flexible and is careless in this paper. Encryption algorithm of high intensity as bilinear mapping is acceptable and Encryption algorithm of low intensity is OK. Meanwhile the security of our system is based on the structure of the system and illegal user cannot decrypt content completely. Also the content is public through Peer-To-Peer network, which makes the system efficient and the pressure of content server is low compared to traditional DRM system.
{"title":"An Efficient Peer-to-Peer Digital Resource Management System for Video Content","authors":"C. Yuan, Yuguang Guo","doi":"10.1109/ISCID.2011.167","DOIUrl":"https://doi.org/10.1109/ISCID.2011.167","url":null,"abstract":"We present a Peer-To-Peer (P2P) Digital Resource Management (DRM) system for video content in this paper. The encryption arithmetic of our system is flexible and is careless in this paper. Encryption algorithm of high intensity as bilinear mapping is acceptable and Encryption algorithm of low intensity is OK. Meanwhile the security of our system is based on the structure of the system and illegal user cannot decrypt content completely. Also the content is public through Peer-To-Peer network, which makes the system efficient and the pressure of content server is low compared to traditional DRM system.","PeriodicalId":224504,"journal":{"name":"2011 Fourth International Symposium on Computational Intelligence and Design","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128387297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PWM (Pulse Width Modulation) is the term used to describe using a digital signal to generate an analogue output signal. This paper is concerned with principles of PWM, PWM Signal Generators and its use in induction motor. At first the principles of PWM and PWM signal generators are discussed. Secondly, a designer's guide to Power MOS Devices for variable speed control of induction motors is analyzed. Lastly, the paper places the emphasis on the simulating of PWM frequency inverter for induction motor. Via the simulation of dynamic process for induction motor, it analyzes the instantaneous characteristics and change law of PWM control technology for induction motor, such as the rotor current, stator current, torque and speed in different PWM input frequency. And the validity of the simulation model is tested and verified via the simulations. The simulation results show that the way through the PWM can be achieved on the induction motor speed modulation.
{"title":"The Pulse Width Modulation and its Use in Induction Motor Speed Control","authors":"Xueqin Lu, Shuguo Chen, Chenning Wu, Mingzhu Li","doi":"10.1109/ISCID.2011.150","DOIUrl":"https://doi.org/10.1109/ISCID.2011.150","url":null,"abstract":"PWM (Pulse Width Modulation) is the term used to describe using a digital signal to generate an analogue output signal. This paper is concerned with principles of PWM, PWM Signal Generators and its use in induction motor. At first the principles of PWM and PWM signal generators are discussed. Secondly, a designer's guide to Power MOS Devices for variable speed control of induction motors is analyzed. Lastly, the paper places the emphasis on the simulating of PWM frequency inverter for induction motor. Via the simulation of dynamic process for induction motor, it analyzes the instantaneous characteristics and change law of PWM control technology for induction motor, such as the rotor current, stator current, torque and speed in different PWM input frequency. And the validity of the simulation model is tested and verified via the simulations. The simulation results show that the way through the PWM can be achieved on the induction motor speed modulation.","PeriodicalId":224504,"journal":{"name":"2011 Fourth International Symposium on Computational Intelligence and Design","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129129539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In order to solve the problem of traditional ASM (Anti-ship Missile) position setting, a new method based on route planning was proposed. According to the concrete targets region a concrete programming project for platform position was determined, the project adopted RRT and AF (Artificial Fish) algorithm, a new method was given to improve the algorithm on its shortcomings. The simulation results verified the validity of this project. The best targets region could be confirmed from the simulation results. When the platform was on the boundary of simulation result, ASM would meet the optimum between the platform survival probability and the fighting efficiency. This method had practical value for the medium and long ASM.
{"title":"Route Planning for Anti-ship Missile Position Setting","authors":"Xingang Wang, Xiaofang Xie","doi":"10.1109/ISCID.2011.47","DOIUrl":"https://doi.org/10.1109/ISCID.2011.47","url":null,"abstract":"In order to solve the problem of traditional ASM (Anti-ship Missile) position setting, a new method based on route planning was proposed. According to the concrete targets region a concrete programming project for platform position was determined, the project adopted RRT and AF (Artificial Fish) algorithm, a new method was given to improve the algorithm on its shortcomings. The simulation results verified the validity of this project. The best targets region could be confirmed from the simulation results. When the platform was on the boundary of simulation result, ASM would meet the optimum between the platform survival probability and the fighting efficiency. This method had practical value for the medium and long ASM.","PeriodicalId":224504,"journal":{"name":"2011 Fourth International Symposium on Computational Intelligence and Design","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123940919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traditional video coding method is able to achieve wonderful performance in data compressing. However, it has high complexity, which is not suitable for some environments where low complexity coding is needed. A new method of video coding which is based on compressive sensing is proposed. In this system, the sparsity of residual of successive frames is exploited, which is a crucial requirement in CS theory. This method encodes video frames in a fast and low-complexity way, while the compressive rate of data remains low. The reconstruction of original video frame, as well as the PSNR-rate curve under this framework, is given.
{"title":"A Low-complexity Video Coding Scheme Based on Compressive Sensing","authors":"Yan-yan Hou, Feng Liu","doi":"10.1109/ISCID.2011.184","DOIUrl":"https://doi.org/10.1109/ISCID.2011.184","url":null,"abstract":"Traditional video coding method is able to achieve wonderful performance in data compressing. However, it has high complexity, which is not suitable for some environments where low complexity coding is needed. A new method of video coding which is based on compressive sensing is proposed. In this system, the sparsity of residual of successive frames is exploited, which is a crucial requirement in CS theory. This method encodes video frames in a fast and low-complexity way, while the compressive rate of data remains low. The reconstruction of original video frame, as well as the PSNR-rate curve under this framework, is given.","PeriodicalId":224504,"journal":{"name":"2011 Fourth International Symposium on Computational Intelligence and Design","volume":"8 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121562533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Convolutional Neural Networks are popularly used in OCR and document recognition. This paper applies stochastic diagonal Levenberg-Marquardt method into a convolutional network, which is presented by Simard. The relations between the sample class number, global learning rate and the network's convergence speed are discussed, Experiments on different train sets showed that class number is an essantial factor to the neural network's convergence. We have successfully expeanded Simard network into recognition of multi-font style little character set like Baidu CAPTCHA and got a recognition rate as 98.4% in single Baidu CAPTCHA character, and 93.5% as the overall rate. Experiments in this paper has confirmed that Convolutional Neural Network can be successfully used in recognition of multi-fontstyle little character set.
{"title":"Recognition of Multi-Fontstyle Characters Based on Convolutional Neural Network","authors":"Gang Lv","doi":"10.1109/ISCID.2011.157","DOIUrl":"https://doi.org/10.1109/ISCID.2011.157","url":null,"abstract":"Convolutional Neural Networks are popularly used in OCR and document recognition. This paper applies stochastic diagonal Levenberg-Marquardt method into a convolutional network, which is presented by Simard. The relations between the sample class number, global learning rate and the network's convergence speed are discussed, Experiments on different train sets showed that class number is an essantial factor to the neural network's convergence. We have successfully expeanded Simard network into recognition of multi-font style little character set like Baidu CAPTCHA and got a recognition rate as 98.4% in single Baidu CAPTCHA character, and 93.5% as the overall rate. Experiments in this paper has confirmed that Convolutional Neural Network can be successfully used in recognition of multi-fontstyle little character set.","PeriodicalId":224504,"journal":{"name":"2011 Fourth International Symposium on Computational Intelligence and Design","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114690322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents an approach to reconstruct instruments with marks. Based on the traditional 3-D reconstruction of single point, we propose a method that reconstructing the marks of the surgery instruments collectively to gain a high positioning accuracy. We match the 2-D projection points, by which the traditional 3-D reconstruction method is used to obtain a rough estimation of the marks' 3-D coordinates. With the structure information, the marks are classified into each instrument. Then, the structure information is used as constraints of the projection functions to reconstruct the marks of one surgery instruments. Experiments conducted on surgery navigation system showed that our method not only reduce the jitter greatly but also improve the accuracy effectively.
{"title":"Instruments' 3-D High-Precision Reconstruction and its Application to Surgery Navigation System","authors":"Yi Shen, Qiankun Zhao, Chenhao Wang, Yuncai Liu","doi":"10.1109/ISCID.2011.140","DOIUrl":"https://doi.org/10.1109/ISCID.2011.140","url":null,"abstract":"This paper presents an approach to reconstruct instruments with marks. Based on the traditional 3-D reconstruction of single point, we propose a method that reconstructing the marks of the surgery instruments collectively to gain a high positioning accuracy. We match the 2-D projection points, by which the traditional 3-D reconstruction method is used to obtain a rough estimation of the marks' 3-D coordinates. With the structure information, the marks are classified into each instrument. Then, the structure information is used as constraints of the projection functions to reconstruct the marks of one surgery instruments. Experiments conducted on surgery navigation system showed that our method not only reduce the jitter greatly but also improve the accuracy effectively.","PeriodicalId":224504,"journal":{"name":"2011 Fourth International Symposium on Computational Intelligence and Design","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126281808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As a relevant topic, improving the sustainability level of urban residential development requires appropriate assessment approaches to be provided. System Dynamics is a computer simulation analysis to understand and discuss complex issues and problems while Analytic Network Process (ANP) is a widely accepted evaluation method used in decision making process with variable comparison and feedback. The purpose of this study is to present an integration approach of System Dynamics (SD) model and ANP method which could better explain the interaction and variation of sustainability indicators. It's able to support the Decision Maker to view sustainability problems of urban residential areas more comprehensively. Furthermore the paper will consider a real case study of the sustainable residential development in urban areas of NanJing China.
{"title":"An ANP-SD Model for the Early Warning Analysis of Sustainable Residential Development","authors":"Zhao Xu","doi":"10.1109/ISCID.2011.23","DOIUrl":"https://doi.org/10.1109/ISCID.2011.23","url":null,"abstract":"As a relevant topic, improving the sustainability level of urban residential development requires appropriate assessment approaches to be provided. System Dynamics is a computer simulation analysis to understand and discuss complex issues and problems while Analytic Network Process (ANP) is a widely accepted evaluation method used in decision making process with variable comparison and feedback. The purpose of this study is to present an integration approach of System Dynamics (SD) model and ANP method which could better explain the interaction and variation of sustainability indicators. It's able to support the Decision Maker to view sustainability problems of urban residential areas more comprehensively. Furthermore the paper will consider a real case study of the sustainable residential development in urban areas of NanJing China.","PeriodicalId":224504,"journal":{"name":"2011 Fourth International Symposium on Computational Intelligence and Design","volume":"2009 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125637778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Calculate the index of Malmquist by use the DEA model, this paper studied the total factor productivity of software enterprises in China from 2007 to 2010.The results show that technological change is the main determinant of total factor productivity index, China must constantly improve technology innovation ability of software industry to make the software industry develop better and faster.
{"title":"Analysis of Total Factor Productivity of China Software Enterprises","authors":"Lei Tong, Yan Lu, Bo Huang","doi":"10.1109/ISCID.2011.176","DOIUrl":"https://doi.org/10.1109/ISCID.2011.176","url":null,"abstract":"Calculate the index of Malmquist by use the DEA model, this paper studied the total factor productivity of software enterprises in China from 2007 to 2010.The results show that technological change is the main determinant of total factor productivity index, China must constantly improve technology innovation ability of software industry to make the software industry develop better and faster.","PeriodicalId":224504,"journal":{"name":"2011 Fourth International Symposium on Computational Intelligence and Design","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132380808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：